Journal article · 2025 · Open access

A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria

Oguche Ajah, Abimbola Helen Afolayan, Akintoba Emmanuel Akinwonmi

International Journal of Applied Information Systems, 12(46), 15–24 · Published 31 January 2025 · DOI 10.5120/ijais2025451987

Open PDFCite this paper

In brief

“A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria” is a 2025 journal article by Oguche Ajah and 2 co-authors, published in International Journal of Applied Information Systems. OpenAlex counts 2 citations as of 20 November 2026, which puts it in the top 6% of works published in 2025 by citations. It is open access: the full text is free to read at International Journal of Applied Information Systems.

Citations
2
Most cited in
2026 (2)
Field-weighted impact
0.40
References
25
Authors
3

Abstract

Heavy rainfall may trigger floods, destroying human life and the agricultural economy.Accurate rainfall forecasting is vital for mitigating the effects of severe flooding.This study compares deep supervised learning (DSL) algorithms for rainfall forecasting in Nigeria, using a large dataset from ECMWF archives that includes Kaduna, Bauchi, Kwara, Imo, Ondo, and Cross River states representing the six geopolitical zones in Nigeria.Critical attributes in the dataset include rainfall, relative humidity, temperature, dew point, surface pressure, and wind speed.Following meticulous preprocessing and outlier removal, feature engineering was done using Pearson correlation and Spearman rank to ensure the most important predictors were chosen.Two sophisticated models-Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) were developed, trained, and tested extensively.The models were assessed using a variety of metrics, including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared, and Accuracy.The findings were impressive, with the GRU model surpassing the LSTM model with the average MSE, MAE, R-Square, RMSE, and Accuracy values of 3.0504, 1.1644, 0.7978, 1.7381, and 98.43%, respectively.These findings illustrate GRU's exceptional capacity to capture complicated patterns of rainfall data, making it an effective tool for meteorological forecasting.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ajah, O., Afolayan, A. H., & Akinwonmi, A. E. (2025). A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria. International Journal of Applied Information Systems, 12(46), 15–24. https://doi.org/10.5120/ijais2025451987

MLA 9

Ajah, Oguche, et al. “A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria.” International Journal of Applied Information Systems, vol. 12, no. 46, 2025, pp. 15–24. https://doi.org/10.5120/ijais2025451987.

Chicago

Ajah, Oguche, Abimbola Helen Afolayan, and Akintoba Emmanuel Akinwonmi. 2025. “A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria.” International Journal of Applied Information Systems 12 (46): 15–24. https://doi.org/10.5120/ijais2025451987.

Harvard

Ajah, O., Afolayan, A. H. and Akinwonmi, A. E. (2025) ‘A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria’, International Journal of Applied Information Systems, 12(46), pp. 15–24. doi:10.5120/ijais2025451987.

IEEE

O. Ajah, A. H. Afolayan, and A. E. Akinwonmi, “A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria,” International Journal of Applied Information Systems, vol. 12, no. 46, pp. 15–24, 2025, doi: 10.5120/ijais2025451987.

BibTeX

@article{ajah2025comparative,
  title     = {{A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria}},
  author    = {Ajah, Oguche and Afolayan, Abimbola Helen and Akinwonmi, Akintoba Emmanuel},
  journal   = {International Journal of Applied Information Systems},
  year      = {2025},
  volume    = {12},
  number    = {46},
  pages     = {15--24},
  doi       = {10.5120/ijais2025451987},
  url       = {https://doi.org/10.5120/ijais2025451987}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI

  • precipitation forecasting
  • long short-term memory
  • gated recurrent unit
  • recurrent neural networks
  • flood control
  • weather forecasting
  • feature selection

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Ajah, O., Afolayan, A. H., & Akinwonmi, A. E. (2025). A Comparative Study of Long Short-Term Memory and Gated Recurrent Units for Forecasting Rainfall: A Case Study of Nigeria. International Journal of Applied Information Systems, 12(46), 15–24. https://doi.org/10.5120/ijais2025451987

How many times has this paper been cited?

2 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Journal of Applied Information Systems: sign in and open the PDF from this page.

Who wrote this paper?

Oguche Ajah, Abimbola Helen Afolayan, Akintoba Emmanuel Akinwonmi.

What is the DOI of this paper?

10.5120/ijais2025451987, permanently at https://doi.org/10.5120/ijais2025451987. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.